Qubex LLM Default Embedder
️⚠️
Heads up!
This embedding model will download (25mb) on the very first embed and runs on CPU. You should have at least 2GB of RAM available to ensure the process does not bottleneck.
Qubex LLM ships with a built-in embedder model that runs on CPU.
The model is the popular all-MiniLM-L6-v2 (opens in a new tab) model, which is primarily trained on English documents.
